Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2bb40be6ef37d52c7142510f189c88b37f8b1b56786b5d2aec7683a25ab42f0
+oid sha256:2a6294ca2205960d4f962c703c57db81d805c5a371ce6bc88be68ee73d00d3c4
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f53f39e1aca6c59aa7c903b32158fc5824f7bbe694cd69a6447a94bea6e67f
+oid sha256:b1d31079fff6a0eacb03770fd3a2a86e7f23c81b80653126b7cf90124787bc52
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca49ab65bc1f6b6e07a97baa271a253688e0cd7d7efd3a4371213104279c9d5b
+oid sha256:1db57d8e4e1bd52139f2e8256eced4f065438475be09434eb594db5df05dca7c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6354288372ec961a9b0cc33d2b16655aaac558d6208ab9ccac75884d564931be
+oid sha256:6a48a141a4823212f57dc573eafe4736af4f057fbff0b82aba3a7d030f51b990
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efef25ea44167287ea83f901a104708084b2ee418ef06071a5130357832811a4
+oid sha256:b7ec91a68ad9db274b6890b9235eb14d6cf9d0f5ef9cb0d59f2b4bded7bf46cd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da7a9ebb8478fa6f89c015f2effdf33c84b179de45b0282ba1809736c74f1a8c
+oid sha256:9e5bfb13000bda3bdbb4097331b55736eb95717d7db54d70276f02093992d973
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
+oid sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3735887110233307,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 1.1822660098522166,
+  "best_metric": 0.36757493019104004,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 1.5763546798029555,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 71.267,
       "eval_steps_per_second": 18.53,
       "step": 75
+    },
+    {
+      "epoch": 1.1980295566502464,
+      "grad_norm": 2.6974918842315674,
+      "learning_rate": 2.3444344707738015e-05,
+      "loss": 0.3408,
+      "step": 76
+    },
+    {
+      "epoch": 1.2137931034482758,
+      "grad_norm": 8.494937896728516,
+      "learning_rate": 2.2400865784401e-05,
+      "loss": 0.4938,
+      "step": 77
+    },
+    {
+      "epoch": 1.2295566502463053,
+      "grad_norm": 3.467758893966675,
+      "learning_rate": 2.1393033535713093e-05,
+      "loss": 0.3987,
+      "step": 78
+    },
+    {
+      "epoch": 1.245320197044335,
+      "grad_norm": 4.509875297546387,
+      "learning_rate": 2.0421950011441354e-05,
+      "loss": 0.4541,
+      "step": 79
+    },
+    {
+      "epoch": 1.2610837438423645,
+      "grad_norm": 4.683701038360596,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 0.4242,
+      "step": 80
+    },
+    {
+      "epoch": 1.276847290640394,
+      "grad_norm": 6.454587459564209,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.488,
+      "step": 81
+    },
+    {
+      "epoch": 1.2926108374384238,
+      "grad_norm": 4.392967700958252,
+      "learning_rate": 1.77396025983391e-05,
+      "loss": 0.3895,
+      "step": 82
+    },
+    {
+      "epoch": 1.3083743842364532,
+      "grad_norm": 5.583901882171631,
+      "learning_rate": 1.6925713641057904e-05,
+      "loss": 0.4257,
+      "step": 83
+    },
+    {
+      "epoch": 1.3241379310344827,
+      "grad_norm": 4.895768165588379,
+      "learning_rate": 1.6153458356909176e-05,
+      "loss": 0.4382,
+      "step": 84
+    },
+    {
+      "epoch": 1.3399014778325122,
+      "grad_norm": 3.4078266620635986,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 0.3986,
+      "step": 85
+    },
+    {
+      "epoch": 1.355665024630542,
+      "grad_norm": 1.3310377597808838,
+      "learning_rate": 1.4737180158065644e-05,
+      "loss": 0.4133,
+      "step": 86
+    },
+    {
+      "epoch": 1.3714285714285714,
+      "grad_norm": 4.339195251464844,
+      "learning_rate": 1.4094705922787687e-05,
+      "loss": 0.4179,
+      "step": 87
+    },
+    {
+      "epoch": 1.387192118226601,
+      "grad_norm": 3.5430753231048584,
+      "learning_rate": 1.3496961026017687e-05,
+      "loss": 0.3472,
+      "step": 88
+    },
+    {
+      "epoch": 1.4029556650246304,
+      "grad_norm": 2.3116374015808105,
+      "learning_rate": 1.2944599093024267e-05,
+      "loss": 0.4153,
+      "step": 89
+    },
+    {
+      "epoch": 1.4187192118226601,
+      "grad_norm": 3.827996015548706,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 0.4521,
+      "step": 90
+    },
+    {
+      "epoch": 1.4344827586206896,
+      "grad_norm": 5.6280622482299805,
+      "learning_rate": 1.1978389830953907e-05,
+      "loss": 0.4921,
+      "step": 91
+    },
+    {
+      "epoch": 1.4502463054187191,
+      "grad_norm": 1.2052680253982544,
+      "learning_rate": 1.1565599037519316e-05,
+      "loss": 0.3844,
+      "step": 92
+    },
+    {
+      "epoch": 1.4660098522167488,
+      "grad_norm": 2.405625820159912,
+      "learning_rate": 1.1200303123839742e-05,
+      "loss": 0.3573,
+      "step": 93
+    },
+    {
+      "epoch": 1.4817733990147783,
+      "grad_norm": 1.4401642084121704,
+      "learning_rate": 1.088290153563358e-05,
+      "loss": 0.3989,
+      "step": 94
+    },
+    {
+      "epoch": 1.4975369458128078,
+      "grad_norm": 3.617347478866577,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 0.4057,
+      "step": 95
+    },
+    {
+      "epoch": 1.5133004926108375,
+      "grad_norm": 3.479245901107788,
+      "learning_rate": 1.0393116880286118e-05,
+      "loss": 0.413,
+      "step": 96
+    },
+    {
+      "epoch": 1.529064039408867,
+      "grad_norm": 3.5945212841033936,
+      "learning_rate": 1.0221269385474488e-05,
+      "loss": 0.4112,
+      "step": 97
+    },
+    {
+      "epoch": 1.5448275862068965,
+      "grad_norm": 4.064784526824951,
+      "learning_rate": 1.0098386775155147e-05,
+      "loss": 0.3898,
+      "step": 98
+    },
+    {
+      "epoch": 1.5605911330049262,
+      "grad_norm": 4.246002197265625,
+      "learning_rate": 1.0024603419658329e-05,
+      "loss": 0.4149,
+      "step": 99
+    },
+    {
+      "epoch": 1.5763546798029555,
+      "grad_norm": 3.537821054458618,
+      "learning_rate": 1e-05,
+      "loss": 0.3968,
+      "step": 100
+    },
+    {
+      "epoch": 1.5763546798029555,
+      "eval_loss": 0.36757493019104004,
+      "eval_runtime": 0.7081,
+      "eval_samples_per_second": 70.613,
+      "eval_steps_per_second": 18.359,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.384195670245376e+17,
+  "total_flos": 3.178927560327168e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null